Google's Threat Intelligence Group just published a snapshot of state-sponsored and criminal actors using LLMs across the full attack lifecycle. The most striking case is PROMPTSPY — an Android backdoor that queries Gemini at runtime to autonomously navigate your phone's UI, intercept biometric gestures, and block its own uninstall. This case study walks through how that works, plus the AI-developed zero-day 2FA bypass, agentic recon frameworks, and LLM-obfuscated malware that round out the report.
CVE-2026-7482 is a critical (CVSS 9.1) unauthenticated heap out-of-bounds read in Ollama's GGUF parser. An attacker uploads a crafted model, calls /api/create, and walks away with your process memory — API keys, system prompts, user conversations, the lot. Around 300,000 internet-exposed Ollama servers are vulnerable. Here's exactly how the bug works, how to check if you're affected, and what to do about it.
A side-by-side comparison of Claude Code, OpenClaw, and NemoClaw — architecture, parallel execution, security, LLM support, and messaging integrations — so you can pick the right AI agent for your use case.
On March 31, 2026, attackers compromised the axios maintainer's npm account and published two malicious versions that dropped a cross-platform remote access trojan via a fake dependency. Here's how the attack worked, how to check if you're affected, and what to do about it.
A full breakdown of the March 2026 LiteLLM supply chain compromise — how attackers weaponized Trivy to backdoor 3.4M daily downloads, the three-stage malware payload, and the exact commands to check if you're affected and recover.
An in-depth look at the Parallelization pattern — executing multiple independent LLM calls, tools, or sub-agents concurrently to drastically reduce latency in agentic systems.
An in-depth look at the Prompt Chaining pattern — breaking complex LLM tasks into sequential, manageable sub-steps for improved reliability, control, and multi-step reasoning.
An in-depth look at the Routing pattern — enabling agents to dynamically direct workflows to specialized tools, sub-agents, or functions based on context and user intent.
An in-depth look at the Parallelization pattern — executing multiple independent LLM calls, tools, or sub-agents concurrently to drastically reduce latency in agentic systems.
An in-depth look at the Prompt Chaining pattern — breaking complex LLM tasks into sequential, manageable sub-steps for improved reliability, control, and multi-step reasoning.
An in-depth look at the Routing pattern — enabling agents to dynamically direct workflows to specialized tools, sub-agents, or functions based on context and user intent.
On March 31, 2026, attackers compromised the axios maintainer's npm account and published two malicious versions that dropped a cross-platform remote access trojan via a fake dependency. Here's how the attack worked, how to check if you're affected, and what to do about it.